Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning
Paper
•
2503.04973
•
Published
•
18
Ming Ryan
yym68686
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
Feature-Level Insights into Artificial Text Detection with Sparse
Autoencoders
upvoted
a
paper
1 day ago
"Principal Components" Enable A New Language of Images
Organizations
None yet
yym68686's activity
upvoted
3
papers
1 day ago
upvoted
an
article
1 day ago
Article
Open R1: Update #3
By
and 9 others
•
•
197
upvoted
2
papers
7 days ago
upvoted
10
papers
15 days ago
YOLOv12: Attention-Centric Real-Time Object Detectors
Paper
•
2502.12524
•
Published
•
10
You Do Not Fully Utilize Transformer's Representation Capacity
Paper
•
2502.09245
•
Published
•
34
Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models
Paper
•
2502.13533
•
Published
•
9
Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data
Paper
•
2502.14044
•
Published
•
7
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
Paper
•
2502.14802
•
Published
•
11
Discovering highly efficient low-weight quantum error-correcting codes with reinforcement learning
Paper
•
2502.14372
•
Published
•
36
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?
Paper
•
2502.14502
•
Published
•
85
TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learning
Paper
•
2502.15425
•
Published
•
8
Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation
Paper
•
2502.16707
•
Published
•
11
Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents
Paper
•
2502.16069
•
Published
•
18
liked
a
Space
17 days ago
liked
a
dataset
20 days ago
upvoted
a
collection
20 days ago
liked
a
Space
22 days ago